Systematic assessment of various universal machine-learning interatomic potentials (2403.05729v3)
Abstract: Machine-learning interatomic potentials have revolutionized materials modeling at the atomic scale. Thanks to these, it is now indeed possible to perform simulations of \abinitio quality over very large time and length scales. More recently, various universal machine-learning models have been proposed as an out-of-box approach avoiding the need to train and validate specific potentials for each particular material of interest. In this paper, we review and evaluate five different universal machine-learning interatomic potentials (uMLIPs), all based on graph neural network architectures which have demonstrated transferability from one chemical system to another. The evaluation procedure relies on data both from a recent verification study of density-functional-theory implementations and from the Materials Project. Through this comprehensive evaluation, we aim to provide guidance to materials scientists in selecting suitable models for their specific research problems, offer recommendations for model selection and optimization, and stimulate discussion on potential areas for improvement in current machine-learning methodologies in materials science.
- Frenkel D, Smit B. Understanding molecular simulation: from algorithms to applications. Elsevier, 2023.
- Hohenberg P, Kohn W. Inhomogeneous Electron Gas. Phys. Rev.. 1964;136(3B):B864-B871. doi: 10.1103/physrev.136.b864
- Kohn W, Sham LJ. Self-Consistent Equations Including Exchange and Correlation Effects. Phys. Rev.. 1965;140(4A):A1133-A1138. doi: 10.1103/physrev.140.a1133
- doi: 10.1038/s41563-021-01013-3
- Goddard I. Classical Force Fields and Methods of Molecular Dynamics:1063–1072; Springer International Publishing . 2021.
- doi: 10.1002/adma.201902765
- Behler J, Parrinello M. Generalized Neural-Network Representation of High-Dimensional Potential-Energy Surfaces. Physical Review Letters. 2007;98(14). doi: 10.1103/physrevlett.98.146401
- doi: 10.1103/physrevlett.104.136403
- doi: 10.1016/j.jcp.2014.12.018
- doi: 10.1063/1.5019779
- Drautz R. Atomic cluster expansion for accurate and transferable interatomic potentials. Physical Review B. 2019;99(1). doi: 10.1103/physrevb.99.014104
- Lilienfeld vOA, Burke K. Retrospective on a decade of machine learning for chemical discovery. Nature Communications. 2020;11(1). doi: 10.1038/s41467-020-18556-9
- doi: 10.1038/s41467-022-29939-5
- Ko TW, Ong SP. Recent advances and outstanding challenges for machine learning interatomic potentials. Nature Computational Science. 2023;3(12):998–1000. doi: 10.1038/s43588-023-00561-9
- doi: 10.1021/acs.chemrev.1c00022
- doi: 10.1021/acs.chemmater.9b01294
- doi: 10.1063/1.4812323
- doi: 10.1103/physrevlett.77.3865
- Chen C, Ong SP. A universal graph deep learning interatomic potential for the periodic table. Nature Computational Science. 2022;2(11):718–728. doi: 10.1038/s43588-022-00349-3
- doi: 10.1038/s42256-023-00716-3
- https://github.com/materialsvirtuallab/matgl; . Accessed: 2024-02-29.
- doi: 10.1039/d2dd00096b
- doi: 10.1038/s41524-020-00440-1
- doi: 10.1088/0953-8984/22/2/022201
- doi: 10.1038/s41586-023-06735-9
- doi: 10.1038/s41467-022-30687-9
- doi: 10.1016/j.jmat.2022.12.007
- doi: 10.1016/j.commatsci.2022.111280
- doi: 10.1039/c6sc05720a
- doi: 10.1038/s41467-019-10827-4
- doi: 10.1126/sciadv.aav6490
- doi: 10.1103/physrevmaterials.7.045802
- Choudhary K, DeCost B. Atomistic Line Graph Neural Network for improved materials property predictions. npj Computational Materials. 2021;7(1). doi: 10.1038/s41524-021-00650-1
- doi: 10.1038/s42254-023-00655-3
- doi: 10.1038/sdata.2018.65
- doi: 10.1016/j.cpc.2019.107042
- doi: 10.1063/1.5144261
- Hamann DR. Optimized norm-conserving Vanderbilt pseudopotentials. Phys. Rev. B. 2013;88(8):085117. doi: 10.1103/physrevb.88.085117
- doi: 10.1016/j.cpc.2018.01.012
- Kresse G, Joubert D. From ultrasoft pseudopotentials to the projector augmented-wave method. Phys. Rev. B. 1999;59:1758–1775. doi: 10.1103/PhysRevB.59.1758
- doi: 10.1063/1.5143061
- Blöchl PE. Projector augmented-wave method. Phys. Rev. B. 1994;50:17953–17979. doi: 10.1103/PhysRevB.50.17953
- Riebesell J. Pymatviz: visualization toolkit for materials informatics. Web Page; 2022. 10.5281/zenodo.7486816 - https://github.com/janosh/pymatviz
- doi: 10.1088/1361-648X/acd831
- Togo A. First-principles Phonon Calculations with Phonopy and Phono3py. J. Phys. Soc. Jpn.. 2023;92(1):012001. doi: 10.7566/JPSJ.92.012001
- doi: 10.1103/physrevb.55.10355
- doi: 10.1103/revmodphys.73.515
- Setyawan W, Curtarolo S. High-throughput electronic band structure calculations: Challenges and tools. Computational Materials Science. 2010;49(2):299–312. doi: 10.1016/j.commatsci.2010.05.010
- doi: 10.1088/1361-648x/aa680e